Skip to main content
main-content
Top

Hint

Swipe to navigate through the chapters of this book

2017 | OriginalPaper | Chapter

6. Iris Segmentation Using Fully Convolutional Encoder–Decoder Networks

Authors: Ehsaneddin Jalilian, Andreas Uhl

Published in: Deep Learning for Biometrics

Publisher: Springer International Publishing

share
SHARE

Abstract

As a considerable breakthrough in artificial intelligence, deep learning has gained great success in resolving key computer vision challenges. Accurate segmentation of the iris region in the eye image plays a vital role in efficient performance of iris recognition systems, as one of the most reliable systems used for biometric identification. In this chapter, as the first contribution, we consider the application of Fully Convolutional Encoder–Decoder Networks (FCEDNs) for iris segmentation. To this extent, we utilize three types of FCEDN architectures for segmentation of the iris in the images, obtained from five different datasets, acquired under different scenarios. Subsequently, we conduct performance analysis, evaluation, and comparison of these three networks for iris segmentation. Furthermore, and as the second contribution, in order to subsidize the true evaluation of the proposed networks, we apply a selection of conventional (non-CNN) iris segmentation algorithms on the same datasets, and similarly evaluate their performances. The results then get compared against those obtained from the FCEDNs. Based on the results, the proposed networks achieve superior performance over all other algorithms, on all datasets.
Footnotes
1
Soft Computing and Image Analysis Lab, Univ. of Beira Interior, UBIRIS.v2 Dataset, see http://​iris.​di.​ubi.​pt/​ubiris1.​html.
 
2
The Center of Biometrics and Security Research, CASIA Iris Image Database, see http://​biometrics.​idealtest.​org.
 
3
Computer Vision Research Lab, Univ. of Notre Dame, Iris Dataset 0405, see https://​sites.​google.​com/​a/​nd.​edu/​public-cvrl/​data-sets.
 
4
The Center of Biometrics and Security Research, CASIA Iris Image Database, see http://​biometrics.​idealtest.​org.
 
5
Indian Institute of Technology Delhi, IIT Delhi Iris Database, see http://​www4.​comp.​polyu.​edu.​hk/​~csajaykr/​database.​php.
 
7
Caffe Deep learning framework, see http://​caffe.​berkeleyvision.​org/​.
 
Literature
1.
go back to reference U. Andreas, W. Peter, Multi-stage visible wavelength and near infrared iris segmentation framework, in Proceedings of the International Conference on Image Analysis and Recognition (ICIAR’12), LNCS (Aveiro, Portugal, 2012), pp. 1–10 U. Andreas, W. Peter, Multi-stage visible wavelength and near infrared iris segmentation framework, in Proceedings of the International Conference on Image Analysis and Recognition (ICIAR’12), LNCS (Aveiro, Portugal, 2012), pp. 1–10
2.
go back to reference V. Badrinarayanan, A. Kendall, R. Cipolla, Segnet: a deep convolutional encoder-decoder architecture for image segmentation (2015), arXiv:​1511.​00561 V. Badrinarayanan, A. Kendall, R. Cipolla, Segnet: a deep convolutional encoder-decoder architecture for image segmentation (2015), arXiv:​1511.​00561
3.
go back to reference L. Bottou, Stochastic gradient descent tricks, in Neural Networks: Tricks of the Trade (Springer, 2012), pp. 421–436 L. Bottou, Stochastic gradient descent tricks, in Neural Networks: Tricks of the Trade (Springer, 2012), pp. 421–436
4.
go back to reference R.P. Broussard, L.R. Kennell, D.L. Soldan, R.W. Ives, Using artificial neural networks and feature saliency techniques for improved iris segmentation, in International Joint Conference on Neural Networks, 2007. IJCNN 2007 (IEEE, 2007), pp. 1283–1288 R.P. Broussard, L.R. Kennell, D.L. Soldan, R.W. Ives, Using artificial neural networks and feature saliency techniques for improved iris segmentation, in International Joint Conference on Neural Networks, 2007. IJCNN 2007 (IEEE, 2007), pp. 1283–1288
5.
go back to reference Y. Chen, M. Adjouadi, A. Barreto, N. Rishe, J. Andrian, A computational efficient iris extraction approach in unconstrained environments, in IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems, 2009. BTAS’09 (IEEE, 2009), pp. 1–7 Y. Chen, M. Adjouadi, A. Barreto, N. Rishe, J. Andrian, A computational efficient iris extraction approach in unconstrained environments, in IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems, 2009. BTAS’09 (IEEE, 2009), pp. 1–7
6.
go back to reference J. Daugman, Recognizing people by their iris patterns. Inf. Secur. Tech. Rep. 3(1), 33–39 (1998) CrossRef J. Daugman, Recognizing people by their iris patterns. Inf. Secur. Tech. Rep. 3(1), 33–39 (1998) CrossRef
7.
go back to reference J. Daugman, How iris recognition works. Int. Conf. Image Process. 1, I-33–I-36 (2002) CrossRef J. Daugman, How iris recognition works. Int. Conf. Image Process. 1, I-33–I-36 (2002) CrossRef
8.
go back to reference J.G. Daugman, High confidence visual recognition of persons by a test of statistical independence. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1148–1161 (1993) CrossRef J.G. Daugman, High confidence visual recognition of persons by a test of statistical independence. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1148–1161 (1993) CrossRef
9.
go back to reference J. Denker, Y. Lecun, Transforming neural-net output levels to probability distributions, in Proceedings of the 3rd International Conference on Neural Information Processing Systems (Morgan Kaufmann Publishers Inc, 1990), pp. 853–859 J. Denker, Y. Lecun, Transforming neural-net output levels to probability distributions, in Proceedings of the 3rd International Conference on Neural Information Processing Systems (Morgan Kaufmann Publishers Inc, 1990), pp. 853–859
10.
go back to reference V. Dorairaj, N.A. Schmid, G. Fahmy, Performance evaluation of non-ideal iris based recognition system implementing global ica encoding, in IEEE International Conference on Image Processing 2005, vol. 3 (IEEE, 2005), pp. III–285 V. Dorairaj, N.A. Schmid, G. Fahmy, Performance evaluation of non-ideal iris based recognition system implementing global ica encoding, in IEEE International Conference on Image Processing 2005, vol. 3 (IEEE, 2005), pp. III–285
11.
13.
go back to reference A. Gangwar, A. Joshi, Deepirisnet: deep iris representation with applications in iris recognition and cross-sensor iris recognition, in 2016 IEEE International Conference on Image Processing (ICIP) (IEEE, 2016), pp. 2301–2305 A. Gangwar, A. Joshi, Deepirisnet: deep iris representation with applications in iris recognition and cross-sensor iris recognition, in 2016 IEEE International Conference on Image Processing (ICIP) (IEEE, 2016), pp. 2301–2305
14.
go back to reference S. Gupta, R. Girshick, P. Arbeláez, J. Malik, Learning rich features from rgb-d images for object detection and segmentation, in European Conference on Computer Vision (Springer, 2014), pp. 345–360 S. Gupta, R. Girshick, P. Arbeláez, J. Malik, Learning rich features from rgb-d images for object detection and segmentation, in European Conference on Computer Vision (Springer, 2014), pp. 345–360
15.
go back to reference B. Hariharan, P. Arbeláez, R. Girshick, J. Malik, Simultaneous detection and segmentation. In European Conference on Computer Vision (Springer, 2014), pp. 297–312 B. Hariharan, P. Arbeláez, R. Girshick, J. Malik, Simultaneous detection and segmentation. In European Conference on Computer Vision (Springer, 2014), pp. 297–312
16.
go back to reference H. Hofbauer, F. Alonso-Fernandez, P. Wild, J. Bigun, A. Uhl, A ground truth for iris segmentation, in Proceedings of the 22nd International Conference on Pattern Recognition (ICPR’14) (Stockholm, Sweden, 2014), 6pp H. Hofbauer, F. Alonso-Fernandez, P. Wild, J. Bigun, A. Uhl, A ground truth for iris segmentation, in Proceedings of the 22nd International Conference on Pattern Recognition (ICPR’14) (Stockholm, Sweden, 2014), 6pp
17.
go back to reference H. Hofbauer, F. Alonso-Fernandez, J. Bigun, A. Uhl, Experimental analysis regarding the influence of iris segmentation on the recognition rate. IET Biom. 5(3), 200–211 (2016) CrossRef H. Hofbauer, F. Alonso-Fernandez, J. Bigun, A. Uhl, Experimental analysis regarding the influence of iris segmentation on the recognition rate. IET Biom. 5(3), 200–211 (2016) CrossRef
18.
go back to reference J. Huang, Y. Wang, T. Tan, J. Cui, A new iris segmentation method for recognition, in (ICPR 2004). Proceedings of the 17th International Conference on Pattern Recognition, 2004, vol. 3 (IEEE, 2004), pp. 554–557 J. Huang, Y. Wang, T. Tan, J. Cui, A new iris segmentation method for recognition, in (ICPR 2004). Proceedings of the 17th International Conference on Pattern Recognition, 2004, vol. 3 (IEEE, 2004), pp. 554–557
19.
20.
go back to reference A. Kendall, V. Badrinarayanan, R. Cipolla, Bayesian segnet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding (2015), arXiv:​1511.​02680 A. Kendall, V. Badrinarayanan, R. Cipolla, Bayesian segnet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding (2015), arXiv:​1511.​02680
21.
go back to reference W. Kong, D. Zhang, Accurate iris segmentation based on novel reflection and eyelash detection model, in Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2001 (IEEE, 2001), pp. 263–266 W. Kong, D. Zhang, Accurate iris segmentation based on novel reflection and eyelash detection model, in Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2001 (IEEE, 2001), pp. 263–266
22.
go back to reference A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (2012), pp. 1097–1105 A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (2012), pp. 1097–1105
23.
go back to reference R.D. Labati, F. Scotti, Noisy iris segmentation with boundary regularization and reflections removal. Image Vis. Comput. 28(2), 270–277 (2010) CrossRef R.D. Labati, F. Scotti, Noisy iris segmentation with boundary regularization and reflections removal. Image Vis. Comput. 28(2), 270–277 (2010) CrossRef
24.
go back to reference Y. Le Cun, D. Touresky, G. Hinton, T. Sejnowski, A theoretical framework for back-propagation, in The Connectionist Models Summer School, vol. 1 (1988), pp. 21–28 Y. Le Cun, D. Touresky, G. Hinton, T. Sejnowski, A theoretical framework for back-propagation, in The Connectionist Models Summer School, vol. 1 (1988), pp. 21–28
25.
go back to reference Y. Le Cun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998) CrossRef Y. Le Cun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998) CrossRef
26.
go back to reference Y.-H. Li, M. Savvides, An automatic iris occlusion estimation method based on high-dimensional density estimation. IEEE Trans. Pattern Anal. Mach. Intell. 35(4), 784–796 (2013) CrossRef Y.-H. Li, M. Savvides, An automatic iris occlusion estimation method based on high-dimensional density estimation. IEEE Trans. Pattern Anal. Mach. Intell. 35(4), 784–796 (2013) CrossRef
27.
go back to reference N. Liu, H. Li, M. Zhang, J. Liu, Z. Sun, T. Tan, Accurate iris segmentation in non-cooperative environments using fully convolutional networks, in 2016 International Conference on Biometrics (ICB) (IEEE, 2016), pp. 1–8 N. Liu, H. Li, M. Zhang, J. Liu, Z. Sun, T. Tan, Accurate iris segmentation in non-cooperative environments using fully convolutional networks, in 2016 International Conference on Biometrics (ICB) (IEEE, 2016), pp. 1–8
28.
go back to reference N. Liu, M. Zhang, H. Li, Z. Sun, T. Tan, Deepiris: learning pairwise filter bank for heterogeneous iris verification. Pattern Recogn. Lett. 82, 154–161 (2016) CrossRef N. Liu, M. Zhang, H. Li, Z. Sun, T. Tan, Deepiris: learning pairwise filter bank for heterogeneous iris verification. Pattern Recogn. Lett. 82, 154–161 (2016) CrossRef
29.
go back to reference X. Liu, K.W. Bowyer, P.J. Flynn, Experiments with an improved iris segmentation algorithm, in Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID’05) (IEEE, 2005), pp. 118–123 X. Liu, K.W. Bowyer, P.J. Flynn, Experiments with an improved iris segmentation algorithm, in Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID’05) (IEEE, 2005), pp. 118–123
30.
go back to reference J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 3431–3440 J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 3431–3440
31.
go back to reference L. Ma, T. Tan, Y. Wang, D. Zhang, Personal identification based on iris texture analysis. IEEE Trans. Pattern Anal. Mach. Intell. 25(12), 1519–1533 (2003) CrossRef L. Ma, T. Tan, Y. Wang, D. Zhang, Personal identification based on iris texture analysis. IEEE Trans. Pattern Anal. Mach. Intell. 25(12), 1519–1533 (2003) CrossRef
32.
go back to reference H. Noh, S. Hong, B. Han, Learning deconvolution network for semantic segmentation, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 1520–1528 H. Noh, S. Hong, B. Han, Learning deconvolution network for semantic segmentation, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 1520–1528
33.
go back to reference D. Petrovska, A. Mayoue, Description and documentation of the biosecure software library, in Project No IST-2002-507634-BioSecure, Deliverable (2007) D. Petrovska, A. Mayoue, Description and documentation of the biosecure software library, in Project No IST-2002-507634-BioSecure, Deliverable (2007)
34.
go back to reference A. Radman, K. Jumari, N. Zainal, Iris segmentation in visible wavelength images using circular gabor filters and optimization. Arab. J. Sci. Eng. 39(4), 3039–3049 (2014) CrossRef A. Radman, K. Jumari, N. Zainal, Iris segmentation in visible wavelength images using circular gabor filters and optimization. Arab. J. Sci. Eng. 39(4), 3039–3049 (2014) CrossRef
35.
go back to reference K.B. Raja, R. Raghavendra, V.K. Vemuri, C. Busch, Smartphone based visible iris recognition using deep sparse filtering. Pattern Recogn. Lett. 57, 33–42 (2015) CrossRef K.B. Raja, R. Raghavendra, V.K. Vemuri, C. Busch, Smartphone based visible iris recognition using deep sparse filtering. Pattern Recogn. Lett. 57, 33–42 (2015) CrossRef
36.
go back to reference C. Rathgeb, A. Uhl, P. Wild, Iris Recognition: From Segmentation to Template Security, vol. 59, Advances in Information Security (Springer, Berlin, 2013) C. Rathgeb, A. Uhl, P. Wild, Iris Recognition: From Segmentation to Template Security, vol. 59, Advances in Information Security (Springer, Berlin, 2013)
37.
go back to reference C. Rathgeb, A. Uhl, P. Wild, H. Hofbauer, Design decisions for an iris recognition sdk, in Handbook of Iris Recognition, 2nd edn., Advances in Computer Vision and Pattern Recognition, ed. by K. Bowyer, M.J. Burge (Springer, Berlin, 2016) CrossRef C. Rathgeb, A. Uhl, P. Wild, H. Hofbauer, Design decisions for an iris recognition sdk, in Handbook of Iris Recognition, 2nd edn., Advances in Computer Vision and Pattern Recognition, ed. by K. Bowyer, M.J. Burge (Springer, Berlin, 2016) CrossRef
38.
go back to reference C.J.V. Rijsbergen, Information Retrieval, 2nd edn. (Butterworth-Heinemann, Newton, 1979) MATH C.J.V. Rijsbergen, Information Retrieval, 2nd edn. (Butterworth-Heinemann, Newton, 1979) MATH
39.
go back to reference T. Rongnian, W. Shaojie, Improving iris segmentation performance via borders recognition, in 2011 International Conference on Intelligent Computation Technology and Automation (ICICTA), vol. 2 (IEEE, 2011), pp. 580–583 T. Rongnian, W. Shaojie, Improving iris segmentation performance via borders recognition, in 2011 International Conference on Intelligent Computation Technology and Automation (ICICTA), vol. 2 (IEEE, 2011), pp. 580–583
40.
go back to reference O. Ronneberger, P. Fischer, T. Brox, U-net: convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention (Springer, 2015), pp. 234–241 O. Ronneberger, P. Fischer, T. Brox, U-net: convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention (Springer, 2015), pp. 234–241
42.
go back to reference N. Srivastava, G.E. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014) MathSciNetMATH N. Srivastava, G.E. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014) MathSciNetMATH
43.
go back to reference C.-W. Tan, A. Kumar, Unified framework for automated iris segmentation using distantly acquired face images. IEEE Trans. Image Process. 21(9), 4068–4079 (2012) MathSciNetCrossRef C.-W. Tan, A. Kumar, Unified framework for automated iris segmentation using distantly acquired face images. IEEE Trans. Image Process. 21(9), 4068–4079 (2012) MathSciNetCrossRef
44.
go back to reference C.-W. Tan, A. Kumar, Towards online iris and periocular recognition under relaxed imaging constraints. IEEE Trans. Image Process. 22(10), 3751–3765 (2013) MathSciNetCrossRef C.-W. Tan, A. Kumar, Towards online iris and periocular recognition under relaxed imaging constraints. IEEE Trans. Image Process. 22(10), 3751–3765 (2013) MathSciNetCrossRef
45.
go back to reference C.-L. Tisse, L. Martin, L. Torres, M. Robert et al., Person identification technique using human iris recognition, in Proceedings of Vision Interface (2002), pp. 294–299 C.-L. Tisse, L. Martin, L. Torres, M. Robert et al., Person identification technique using human iris recognition, in Proceedings of Vision Interface (2002), pp. 294–299
47.
go back to reference A. Uhl, P. Wild, Weighted adaptive hough and ellipsopolar transforms for real-time iris segmentation, in Proceedings of the 5th IAPR/IEEE International Conference on Biometrics (ICB’12) (New Delhi, India, 2012), pp. 1–8 A. Uhl, P. Wild, Weighted adaptive hough and ellipsopolar transforms for real-time iris segmentation, in Proceedings of the 5th IAPR/IEEE International Conference on Biometrics (ICB’12) (New Delhi, India, 2012), pp. 1–8
48.
go back to reference P. Wild, H. Hofbauer, J. Ferryman, A. Uhl, Segmentation-level fusion for iris recognition, in Proceedings of the International Conference of the Biometrics Special Interest Group (BIOSIG’15) (Darmstadt, Germany, 2015), p. 12 P. Wild, H. Hofbauer, J. Ferryman, A. Uhl, Segmentation-level fusion for iris recognition, in Proceedings of the International Conference of the Biometrics Special Interest Group (BIOSIG’15) (Darmstadt, Germany, 2015), p. 12
49.
go back to reference R.P. Wildes, Iris recognition: an emerging biometric technology. Proc. IEEE 85(9), 1348–1363 (1997) CrossRef R.P. Wildes, Iris recognition: an emerging biometric technology. Proc. IEEE 85(9), 1348–1363 (1997) CrossRef
50.
go back to reference Z. Zhao, K. Ajay, An accurate iris segmentation framework under relaxed imaging constraints using total variation model, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 3828–3836 Z. Zhao, K. Ajay, An accurate iris segmentation framework under relaxed imaging constraints using total variation model, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 3828–3836
51.
go back to reference J. Zuo, N. D. Kalka, N.A. Schmid, A robust iris segmentation procedure for unconstrained subject presentation, in 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference (IEEE, 2006), pp. 1–6 J. Zuo, N. D. Kalka, N.A. Schmid, A robust iris segmentation procedure for unconstrained subject presentation, in 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference (IEEE, 2006), pp. 1–6
Metadata
Title
Iris Segmentation Using Fully Convolutional Encoder–Decoder Networks
Authors
Ehsaneddin Jalilian
Andreas Uhl
Copyright Year
2017
DOI
https://doi.org/10.1007/978-3-319-61657-5_6

Premium Partner